A Perspective on Deep Learning for Molecular Modeling and Simulations

Abstract

Deep learning is transforming many areas in science, and it has great potential in modeling molecular systems. However, unlike the mature deployment of deep learning in computer vision and natural language processing, its development in molecular modeling and simulations is still at an early stage, largely because the inductive biases of molecules are completely different from those of images or texts. Footed on these differences, we first reviewed the limitations of traditional deep learning models from the perspective of molecular physics, and wrapped up some relevant technical advancement at the interface between molecular modeling and deep learning. We do not focus merely on the ever more complex neural network models, instead, we emphasize the theories and ideas behind modern deep learning. We hope that transacting these ideas into molecular modeling will create new opportunities. For this purpose, we summarized several representative applications, ranging from supervised to unsupervised and reinforcement learning, and discussed their connections with the emerging trends in deep learning. Finally, we outlook promising directions which may help address the existing issues in the current framework of deep molecular modeling.

References in corpus (40)

• Deep Learning in Neural Networks: An Overview
• Auto-Encoding Variational Bayes
• Continuous control with deep reinforcement learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Variational Inference: A Review for Statisticians
• Neural Message Passing for Quantum Chemistry
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Spectral Normalization for Generative Adversarial Networks
• Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Self-Attention Generative Adversarial Networks
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• An Overview of Multi-Task Learning in Deep Neural Networks
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• NICE: Non-linear Independent Components Estimation
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Machine Learning Unifies the Modelling of Materials and Molecules
• Density estimation using Real NVP
• Interaction Networks for Learning about Objects, Relations and Physics
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• VAMPnets: Deep learning of molecular kinetics
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• A Variational Approach to Enhanced Sampling and Free Energy Calculations
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Entropy based fingerprint for local crystalline order
• Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
• Neural networks-based variationally enhanced sampling
• Using the Maximum Entropy Principle to Combine Simulations and Solution Experiments
• Reinforced dynamics for enhanced sampling in large atomic and molecular systems
• Neural network based path collective variables for enhanced sampling of phase transformations
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Implicit Generation and Generalization in Energy-Based Models
• PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials
• Learning Clustered Representation for Complex Free Energy Landscapes

Cited by in corpus (5)

• Deep Reinforcement Learning of Transition States
• Fewest-Switches Surface Hopping with Long Short-Term Memory Networks
• Transferable and Robust Machine Learning Model for Predicting Stability of Si Anodes for Multivalent Cation Batteries
• Mean-Field Density Matrix Decompositions
• A Sinking Approach to Explore Arbitrary Areas in Free Energy Landscapes